Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 4-LLAMASCOPE-RES-32K
    6. 30974
    Prev
    Next
    INDEX
    Explanations

    mentions of streaming platforms and music-related services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reno
    -0.15
    ãĤĵãģ©
    -0.15
    çĸ
    -0.15
    ãģŁãģı
    -0.15
    grav
    -0.14
    .ManyToMany
    -0.14
    mens
    -0.14
     grav
    -0.14
     Sense
    -0.14
    ãĤıãģij
    -0.14
    POSITIVE LOGITS
    wat
    0.15
    24
    0.14
    à¸ĩศ
    0.14
    rat
    0.14
    isa
    0.14
     returned
    0.13
    STRUCTOR
    0.13
    ableObject
    0.13
    30
    0.13
     consideration
    0.13
    Activations Density 0.142%

    No Known Activations